{"title":"Design of a compact alignment tolerant optical interconnect for photonic backplane applications","authors":"B. Robertson","doi":"10.1109/MPPOI.1997.609108","DOIUrl":"https://doi.org/10.1109/MPPOI.1997.609108","url":null,"abstract":"This paper describes a compact alignment tolerant interconnect designed for use within a prototype modulator based photonic backplane. To simplify the optical design, the optical input and output of each smart pixel array are clustered separately, thereby allowing a Fourier-plane patterned mirror array to be used in the beam-routing optics. The primary advantages of this scheme are the simplicity of the optical design and the alignability associated with clustered window microchannel relay systems making it ideally suited for high density interconnection applications.","PeriodicalId":406486,"journal":{"name":"Proceedings of the Fourth International Conference on Massively Parallel Processing Using Optical Interconnections","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1997-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128032058","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Inexpensive local interconnect solutions using side-coupling polymer optical fibers","authors":"Y. Li, Ting Wang, K. Fasanella","doi":"10.1109/MPPOI.1997.609089","DOIUrl":"https://doi.org/10.1109/MPPOI.1997.609089","url":null,"abstract":"Potentially low-cost optical side-couplers embedded along a polymer optical fiber are demonstrated using etched micro-mirrors. Both serial and parallel mirror fabrication possibilities are discussed. Near uniform light distributions to as many as 256 such side-coupling ports along a single straight fiber were experimentally obtained. Various unidirectional and bi-directional all plastic array coupler concepts are presented. Some of them are experimentally demonstrated. Low-cost unidirectional and bidirectional optical data buses are proposed.","PeriodicalId":406486,"journal":{"name":"Proceedings of the Fourth International Conference on Massively Parallel Processing Using Optical Interconnections","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1997-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134154125","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"HADLOP-a hardware description language for the design of digital 3-D optoelectronic circuits","authors":"Guido Grimm, Marko Degenkolb, Dietmar Fey","doi":"10.1109/MPPOI.1997.609114","DOIUrl":"https://doi.org/10.1109/MPPOI.1997.609114","url":null,"abstract":"A tool for computer-aided design and simulation of digital 3-D optoelectronic computing systems is presented. The program especially considers the features offered by the optics. The usefulness and the large flexibility of the tool was demonstrated exemplary for both architecture proposals published in literature and own proposals. The simulation system is freeware and is available via the Internet http://www2.informatik.uni-jena.de/pope/HADLOP/hadlop.html.","PeriodicalId":406486,"journal":{"name":"Proceedings of the Fourth International Conference on Massively Parallel Processing Using Optical Interconnections","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1997-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134363543","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Free-space optical interconnections within SIMD massively parallel computers","authors":"P. Scheer, T. Collette, P. Churoux","doi":"10.1109/MPPOI.1997.609185","DOIUrl":"https://doi.org/10.1109/MPPOI.1997.609185","url":null,"abstract":"Multi-level electronic integration of massively parallel computers leads to latency effects and I/O bottlenecks. A new implementation scheme using MCM-to-MCM free-space optical interconnects is discussed in terms of architecture enhancement, system modeling and technical challenges. Building blocks of an experimental demonstrator including zero-biased-VCSEL with hybridized microlenses are also presented.","PeriodicalId":406486,"journal":{"name":"Proceedings of the Fourth International Conference on Massively Parallel Processing Using Optical Interconnections","volume":"74 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1997-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123805964","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Y. Joo, S. Fike, K. Chung, M. Brooke, N. Jokerst, D. Wills
{"title":"Application of massively parallel processors to real time processing of high speed images","authors":"Y. Joo, S. Fike, K. Chung, M. Brooke, N. Jokerst, D. Wills","doi":"10.1109/MPPOI.1997.609129","DOIUrl":"https://doi.org/10.1109/MPPOI.1997.609129","url":null,"abstract":"This paper demonstrates that the real-time utilization of image sequences, at frame rates far above what is currently possible, can now be achieved with an optically interconnected massively parallel processor. A focal plane processing chip with an on-chip array of sigma-delta analog to digital converter front ends under each pixel is presented. This two layer chip is a scaleable high frame rate image capture building block, however it requires a third layer of data processing to filter the sigma-delta front end data to obtain images. The use of an array of optically connected processors beneath the chip proves to be the best solution to this challenging data processing task.","PeriodicalId":406486,"journal":{"name":"Proceedings of the Fourth International Conference on Massively Parallel Processing Using Optical Interconnections","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1997-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121514006","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Experimental verification of the pulse shepherding concept in dispersion-shifted single-mode fiber for bit-parallel wavelength links","authors":"L. Bergman, J. Morookian, C. Yeh, S. Monacos","doi":"10.1109/MPPOI.1997.609071","DOIUrl":"https://doi.org/10.1109/MPPOI.1997.609071","url":null,"abstract":"A new way to dynamically control in-flight pulses by a co-propagating shepherd pulse in a wavelength division multiplexed (WDM) single-mode fiber system was proposed at the MPPOI '96 Conference. That system functionally resembles an optical fiber ribbon cable, except that all the bits pass on one fiber optic waveguide. This single fiber bit parallel wavelength link can be used to extend the (speed x distance) product of emerging cluster computer networks, such as, the MyriNet, SCI, Hippi-6400, ShuffleNet, etc. Here, we shall present the first experimental evidence that this pulse shepherding effect can be observed in a commercially available Corning DS (dispersion-shifted) fiber. Computer simulation results will first be presented for the case observed in the laboratory setup. A discussion of the experiment setup and measurement procedures will be given. Experimental results will then be compared with computer generated results. Excellent agreement is observed. Future experiments dealing with the shepherding effect among more than two co-propagating pulses will be performed.","PeriodicalId":406486,"journal":{"name":"Proceedings of the Fourth International Conference on Massively Parallel Processing Using Optical Interconnections","volume":"142 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1997-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133635526","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Switches and switch interconnects","authors":"L.M. Ni, Wenjian Qiao, Mingyao Yang","doi":"10.1109/MPPOI.1997.609151","DOIUrl":"https://doi.org/10.1109/MPPOI.1997.609151","url":null,"abstract":"Switched networks are receiving much attention and supplying a major class of interconnect networks. This paper discusses major issues in switch design and switch interconnects. Due to the importance of high-speed switches in building switched LANs, major design issues are studied and several commercial switches are reviewed. Among different techniques used in switch design, cut-through switching promises short latency delivery and thus is well suited to distributed/parallel applications. The back pressure flow control of cut-through switching also prevents packet loss due to buffer overflow. For economical and practical reasons, switch interconnects should support irregular topologies, which makes deadlock-free routing more difficult. To provide good network performance, a key point is to develop a traffic-balanced network with minimum diameter and average path length. It is important to understand the issues and solutions in these areas in order to meet the increasing performance demand.","PeriodicalId":406486,"journal":{"name":"Proceedings of the Fourth International Conference on Massively Parallel Processing Using Optical Interconnections","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1997-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131310360","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"8.5 Gbit/s/port synchronous optical packet-switch","authors":"Y. Maeno, A. Tajima, Y. Suemura, N. Henmi","doi":"10.1109/MPPOI.1997.609146","DOIUrl":"https://doi.org/10.1109/MPPOI.1997.609146","url":null,"abstract":"A synchronous optical network interconnecting processor effectively reduces network latency and enhances bandwidth. If however, synchronization is not accurate and stable, skew and jitter in received packets may cause transmission errors. Timing margin design must consider the tolerance of the receiver to the skew and jitter. A theoretical analysis shows that the tolerance is /spl plusmn/12% of a bit period. Synchronization by clock distribution is achieved on an 8.5 Gbit/s/port packet-switch testbed utilizing semiconductor optical amplifier gates. An experiment shows that the sensitivity penalty induced by removing the preamble from the packet header and suppressing guard time is less than 0.5 dB.","PeriodicalId":406486,"journal":{"name":"Proceedings of the Fourth International Conference on Massively Parallel Processing Using Optical Interconnections","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1997-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131372894","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Commercial MPP networks: Time for optics?","authors":"C. Stunkel","doi":"10.1109/MPPOI.1997.609123","DOIUrl":"https://doi.org/10.1109/MPPOI.1997.609123","url":null,"abstract":"Today's commercial MPP machines do not employ optics within their interconnection networks. In this paper we identify several recent trends in MPP networks and attempt to predict how these trends will affect the incorporation of optical interconnect technologies in the near future. We also recognize that successful commercial systems tend to change in an evolutionary fashion, and some possible evolutionary scenarios are discussed.","PeriodicalId":406486,"journal":{"name":"Proceedings of the Fourth International Conference on Massively Parallel Processing Using Optical Interconnections","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1997-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130320935","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Optics inside future computers","authors":"C. Lund","doi":"10.1109/MPPOI.1997.609174","DOIUrl":"https://doi.org/10.1109/MPPOI.1997.609174","url":null,"abstract":"This paper discusses the potential role of optics in future COTS processors manufactured by Mercury Computer Systems. We conclude that high-end applications, particularly space time adaptive processing (STAP), benefit from a computing platform with an optical backplane.","PeriodicalId":406486,"journal":{"name":"Proceedings of the Fourth International Conference on Massively Parallel Processing Using Optical Interconnections","volume":"90 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1997-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132975808","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}